Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    condition checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ามารถ
    0.41
    吶
    0.41
     смогут
    0.38
     රස
    0.38
    राहुल
    0.38
    सरत
    0.38
     dilengkapi
    0.38
    ूटूथ
    0.37
     আদৌ
    0.37
     сможет
    0.37
    POSITIVE LOGITS
     Flat
    0.42
     già
    0.40
     already
    0.40
     deja
    0.38
     Nothing
    0.38
     graz
    0.38
     flat
    0.38
     déjà
    0.37
    already
    0.37
     simplic
    0.37
    Act Density 0.061%

    No Known Activations